Bitcoin has recently received a lot of attention from the media and the public due to its recent price surge and crash. Correspondingly, many researchers have investigated various factors that affect the Bitcoin price and the patterns behind its fluctuations, in particular, using various machine learning methods. In this paper, we study and compare various state-of-the-art deep learning methods such as a deep neural network (DNN), a long short-term memory (LSTM) model, a convolutional neural network, a deep residual network, and their combinations for Bitcoin price prediction. Experimental results showed that although LSTM-based prediction models slightly outperformed the other prediction models for Bitcoin price prediction (regression), DNN-based models performed the best for price ups and downs prediction (classification). In addition, a simple profitability analysis showed that classification models were more effective than regression models for algorithmic trading. Overall, the performances of the proposed deep learning-based prediction models were comparable.

Blockchain technology, which provides digital security in a distributed manner, has evolved into a key technology that can build efficient and reliable decentralized applications (called DApps) beyond the function of cryptocurrency. The characteristics of blockchain such as immutability and openness, however, have made DApps more vulnerable to various security risks, and thus it has become of great significance to validate the integrity of DApps before they actually operate upon blockchain. Recently, research on vulnerability in smart contracts (a building block of DApps) has been actively conducted, and various vulnerabilities and their countermeasures were reported. However, the effectiveness of such countermeasures has not been studied well, and no appropriate methods have been proposed to evaluate them. In this paper, we propose a software tool that can easily perform comparative studies by adding existing/new countermeasures and labeled smart contract codes. The proposed tool demonstrates verification performance using various statistical indicators, which helps to identify the most effective countermeasures for each type of vulnerability. Using the proposed tool, we evaluated state-of-the-art countermeasures with 237 labeled benchmark codes. The results indicate that for certain types of vulnerabilities, some countermeasures show evenly good performance scores on various metrics. However, it is also observed that countermeasures that detect the largest number of vulnerable codes typically generate much more false positives, resulting in very low precision and accuracy. Consequently, under given constraints, different countermeasures may be recommended for detecting vulnerabilities of interest. We believe that the proposed tool could effectively be utilized for a future verification study of smart contract applications and contribute to the development of practical and secure smart contract applications.

The advancement of neural-based models has driven significant progress in modern code intelligence, accelerating the development of intelligent programming tools such as code assistants and automated software engineering systems. This study presents a comprehensive and systematic survey of neural methods for programming tasks within the broader context of software development. Guided by six research questions, this study synthesizes insights from more than 250 scientific papers, the majority of which were published between 2015 and 2025, with earlier foundational works (dating back to the late 1990s) included for historical context. The analysis spans 18 major programming tasks, including code generation, code translation, code clone detection, code classification, and vulnerability detection. The survey methodologically examines the development and evolution of neural approaches, the datasets employed, and the performance evaluation metrics adopted in this field. It traces the progress in neural techniques from early code modeling approaches to advanced Code-specific Large Language Models (Code LLMs), emphasizing their advantages over traditional rule-based and statistical methods. A taxonomy of evaluation metrics and a categorized summary of datasets and benchmarks reveal both progress and persistent limitations in data coverage and evaluation practices. The review further distinguishes neural models designed for natural language processing and programming languages, highlighting the structural and functional characteristics that influence model performance. Finally, the study discusses emerging trends, unresolved challenges, and potential research directions, underscoring the transformative role of neural-based architectures, particularly Code LLMs, in enhancing programming and software design activities and shaping the future of AI-driven software development.

Identifying the point of error is imperative in software debugging. Traditional fault localization (FL) techniques rely on executing the program and using the code coverage matrix in tandem with test case results to calculate a suspiciousness score for each function or line. Recently, learning-based FL techniques have harnessed machine learning models to extract meaningful features from the code coverage matrix and improve FL performance. These techniques, however, require compilable source code, existing test cases, and specialized tools for generating the code coverage matrix for each programming language of interest. In this paper, we propose, for the first time, a simple but effective sequence generation approach for fine-tuning large language models of code (LLMCs) for FL tasks. LLMCs have recently received much attention for various software engineering problems. In line with these, we leverage the innate understanding of code that LLMCs have acquired through pre-training on large code corpora. Specifically, we fine-tune representative encoder, encoder-decoder, and decoder-based 13 LLMCs for FL tasks. Unlike previous approaches, LLMCs can analyze code sequences even with syntactic errors, since they do not rely on compiled input. Still, they have a limitation on the length of the input data. Therefore, for a fair comparison with existing FL techniques, we extract methods with errors from the project-level benchmark, Defects4J, and analyze them at the line level. Experimental results show that LLMCs fine-tuned with our approach successfully pinpoint error positions in 50.6\%, 64.2\%, and 72.3\% of 1,291 methods in Defects4J for Top-1/3/5 prediction, outperforming the best learning-based state-of-the-art technique by up to 1.35, 1.12, and 1.08 times, respectively. Our findings suggest promising research directions for FL and automated program repair tasks using LLMCs.